Compare commits

..
10 changed files with 65 additions and 219 deletions
-18
View File
@@ -1,18 +0,0 @@
# CARTO's Changelog
## v1.2.0-carto.2
Released 2018-10-26
Bug fixes:
* Make all modules to use strict mode semantics.
## v1.2.0-carto.1
Released 2018-06-11
Bug fixes:
* Improves performance of COPY TO by sending bigger chunks through low level `push()`. See https://github.com/CartoDB/node-pg-copy-streams/pull/1
## v1.2.0
Released 2016-08-22
Vanilla version v1.2.0 from upstream repository. See https://github.com/CartoDB/node-pg-copy-streams/releases/tag/v1.2.0
+2 -10
View File
@@ -42,15 +42,10 @@ pg.connect(function(err, client, done) {
var stream = client.query(copyFrom('COPY my_table FROM STDIN'));
var fileStream = fs.createReadStream('some_file.tsv')
fileStream.on('error', done);
stream.on('error', done);
stream.on('end', done);
fileStream.pipe(stream);
fileStream.pipe(stream).on('finish', done).on('error', done);
});
```
*Important*: Even if `pg-copy-streams.from` is used as a Writable (via `pipe`), you should not listen for the 'finish' event and expect that the COPY command has already been correctly acknowledged by the database. Internally, a duplex stream is used to pipe the data into the database connection and the COPY command should be considered complete only when the 'end' event is triggered.
## install
```sh
@@ -61,10 +56,7 @@ $ npm install pg-copy-streams
This module __only__ works with the pure JavaScript bindings. If you're using `require('pg').native` please make sure to use normal `require('pg')` or `require('pg.js')` when you're using copy streams.
Before you set out on this magical piping journey, you _really_ should read this: http://www.postgresql.org/docs/current/static/sql-copy.html, and you might want to take a look at the [tests](https://github.com/brianc/node-pg-copy-streams/tree/master/test) to get an idea of how things work.
Take note of the following warning in the PostgreSQL documentation:
> COPY stops operation at the first error. This should not lead to problems in the event of a COPY TO, but the target table will already have received earlier rows in a COPY FROM. These rows will not be visible or accessible, but they still occupy disk space. This might amount to a considerable amount of wasted disk space if the failure happened well into a large copy operation. You might wish to invoke VACUUM to recover the wasted space.
Before you set out on this magical piping journey, you _really_ should read this: http://www.postgresql.org/docs/9.3/static/sql-copy.html, and you might want to take a look at the [tests](https://github.com/brianc/node-pg-copy-streams/tree/master/test) to get an idea of how things work.
## contributing
+38 -67
View File
@@ -1,17 +1,14 @@
'use strict';
module.exports = function(txt, options) {
return new CopyStreamQuery(txt, options)
}
var Transform = require('stream').Transform
var util = require('util')
var code = require('./message-formats')
var CopyStreamQuery = function(text, options) {
Transform.call(this, options)
this.text = text
this._gotCopyOutResponse = false
this._copyOutResponse = null
this.rowCount = 0
}
@@ -26,89 +23,63 @@ CopyStreamQuery.prototype.submit = function(connection) {
connection.stream.pipe(this)
}
var code = {
E: 69, //Error
H: 72, //CopyOutResponse
d: 0x64, //CopyData
c: 0x63 //CopyDone
}
CopyStreamQuery.prototype._detach = function() {
this.connection.stream.unpipe(this)
// Unpipe can drop us out of flowing mode
this.connection.stream.resume()
}
CopyStreamQuery.prototype._transform = function(chunk, enc, cb) {
var offset = 0
var Byte1Len = 1;
var Int32Len = 4;
if(this._remainder && chunk) {
chunk = Buffer.concat([this._remainder, chunk])
}
var length;
var messageCode;
var needPush = false;
var buffer = Buffer.alloc(chunk.length);
var buffer_offset = 0;
this.pushBufferIfneeded = function() {
if (needPush && buffer_offset > 0) {
this.push(buffer.slice(0, buffer_offset))
buffer_offset = 0;
}
}
while((chunk.length - offset) >= (Byte1Len + Int32Len)) {
var messageCode = chunk[offset]
//console.log('PostgreSQL message ' + String.fromCharCode(messageCode))
switch(messageCode) {
// detect COPY start
case code.CopyOutResponse:
if (!this._gotCopyOutResponse) {
this._gotCopyOutResponse = true
} else {
this.emit('error', new Error('Unexpected CopyOutResponse message (H)'))
}
break;
// meaningful row
case code.CopyData:
needPush = true;
break;
// standard interspersed messages. discard
case code.ParameterStatus:
case code.NoticeResponse:
case code.NotificationResponse:
break;
case code.ErrorResponse:
case code.CopyDone:
this.pushBufferIfneeded();
if(!this._copyOutResponse) {
this._copyOutResponse = true
if(chunk[0] == code.E) {
this._detach()
this.push(null)
return cb();
break;
default:
this.emit('error', new Error('Unexpected PostgreSQL message ' + String.fromCharCode(messageCode)))
}
length = chunk.readUInt32BE(offset+Byte1Len)
if(chunk.length >= (offset + Byte1Len + length)) {
offset += Byte1Len + Int32Len
if (needPush) {
var row = chunk.slice(offset, offset + length - Int32Len)
if(chunk[0] != code.H) {
this.emit('error', new Error('Expected copy out response'))
}
var length = chunk.readUInt32BE(1)
offset = 1
offset += length
}
while((chunk.length - offset) > 5) {
var messageCode = chunk[offset]
//complete or error
if(messageCode == code.c || messageCode == code.E) {
this._detach()
this.push(null)
return cb();
}
//something bad happened
if(messageCode != code.d) {
return this.emit('error', new Error('expected "d" (copydata message)'))
}
var length = chunk.readUInt32BE(offset + 1) - 4 //subtract length of UInt32
//can we read the next row?
if(chunk.length > (offset + length + 5)) {
offset += 5
var slice = chunk.slice(offset, offset + length)
offset += length
this.push(slice)
this.rowCount++
row.copy(buffer, buffer_offset);
buffer_offset += row.length;
}
offset += (length - Int32Len)
} else {
// we need more chunks for a complete message
break;
}
}
this.pushBufferIfneeded();
if(chunk.length - offset) {
var slice = chunk.slice(offset)
this._remainder = slice
+16 -26
View File
@@ -1,5 +1,3 @@
'use strict';
var CopyToQueryStream = require('./copy-to')
module.exports = {
to: function(txt, options) {
@@ -12,7 +10,6 @@ module.exports = {
var Transform = require('stream').Transform
var util = require('util')
var code = require('./message-formats')
var CopyStreamQuery = function(text, options) {
Transform.call(this, options)
@@ -29,23 +26,28 @@ CopyStreamQuery.prototype.submit = function(connection) {
connection.query(this.text)
}
var code = {
H: 72, //CopyOutResponse
d: 0x64, //CopyData
c: 0x63 //CopyDone
}
var copyDataBuffer = Buffer([code.CopyData])
var copyDataBuffer = Buffer([code.d])
CopyStreamQuery.prototype._transform = function(chunk, enc, cb) {
var Int32Len = 4;
this.push(copyDataBuffer)
var lenBuffer = Buffer(Int32Len)
lenBuffer.writeUInt32BE(chunk.length + Int32Len, 0)
var lenBuffer = Buffer(4)
lenBuffer.writeUInt32BE(chunk.length + 4, 0)
this.push(lenBuffer)
this.push(chunk)
this.rowCount++
cb()
}
CopyStreamQuery.prototype._flush = function(cb) {
var Int32Len = 4;
var finBuffer = Buffer([code.CopyDone, 0, 0, 0, Int32Len])
var finBuffer = Buffer([code.c, 0, 0, 0, 4])
this.push(finBuffer)
this.cb_flush = cb
//never call this callback, do not close underlying stream
//cb()
}
CopyStreamQuery.prototype.handleError = function(e) {
@@ -53,24 +55,12 @@ CopyStreamQuery.prototype.handleError = function(e) {
}
CopyStreamQuery.prototype.handleCopyInResponse = function(connection) {
this.pipe(connection.stream, { end: false })
this.pipe(connection.stream)
}
CopyStreamQuery.prototype.handleCommandComplete = function(msg) {
// Parse affected row count as in
// https://github.com/brianc/node-postgres/blob/35e5567f86774f808c2a8518dd312b8aa3586693/lib/result.js#L37
var match = /COPY (\d+)/.exec((msg || {}).text)
if (match) {
this.rowCount = parseInt(match[1], 10)
}
// we delay the _flush cb so that the 'end' event is
// triggered after CommandComplete
this.cb_flush()
// unpipe from connection
this.unpipe(this.connection)
this.connection = null
CopyStreamQuery.prototype.handleCommandComplete = function() {
this.unpipe()
this.emit('end')
}
CopyStreamQuery.prototype.handleReadyForQuery = function() {
-25
View File
@@ -1,25 +0,0 @@
/**
* The COPY feature uses the following protocol codes.
* The codes for the most recent protocol version are documented on
* https://www.postgresql.org/docs/current/static/protocol-message-formats.html
*
* The protocol flow itself is described on
* https://www.postgresql.org/docs/current/static/protocol-flow.html
*/
module.exports = {
ErrorResponse: 0x45, // E
CopyInResponse: 0x47, // G
CopyOutResponse: 0x48, // H
CopyBothResponse: 0x57, // W
CopyDone: 0x63, // c
CopyData: 0x64, // d
CopyFail: 0x66, // f
// It is possible for NoticeResponse and ParameterStatus messages to be interspersed between CopyData messages;
// frontends must handle these cases, and should be prepared for other asynchronous message types as well
// (see Section 50.2.6).
// Otherwise, any message type other than CopyData or CopyDone may be treated as terminating copy-out mode.
NotificationResponse: 0x41, // A
NoticeResponse: 0x4E, // N
ParameterStatus: 0x53 // S
}
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "pg-copy-streams",
"version": "1.2.0-carto.2",
"version": "0.3.0",
"description": "Low-Level COPY TO and COPY FROM streams for PostgreSQL in JavaScript using",
"main": "index.js",
"scripts": {
+2 -4
View File
@@ -1,5 +1,3 @@
'use strict';
var assert = require('assert')
var gonna = require('gonna')
@@ -21,7 +19,7 @@ var testBinaryCopy = function() {
var fromClient = client()
var toClient = client()
var queries = [
queries = [
'DROP TABLE IF EXISTS data',
'CREATE TABLE IF NOT EXISTS data (num BIGINT, word TEXT)',
'INSERT INTO data (num, word) VALUES (1, \'hello\'), (2, \'other thing\'), (3, \'goodbye\')',
@@ -35,7 +33,7 @@ var testBinaryCopy = function() {
var fromStream = fromClient.query(to('COPY (SELECT * FROM data) TO STDOUT BINARY'))
var toStream = toClient.query(from('COPY data_copy FROM STDIN BINARY'))
var runStream = function(callback) {
runStream = function(callback) {
fromStream.on('error', callback)
toStream.on('error', callback)
toStream.on('finish', callback)
+4 -19
View File
@@ -1,5 +1,3 @@
'use strict';
var assert = require('assert')
var gonna = require('gonna')
@@ -32,6 +30,10 @@ var testRange = function(top) {
var txt = 'COPY numbers FROM STDIN'
var stream = fromClient.query(copy(txt))
var rowEmitCount = 0
stream.on('row', function() {
rowEmitCount++
})
for(var i = 0; i < top; i++) {
stream.write(Buffer('' + i + '\t' + i*10 + '\n'))
}
@@ -41,7 +43,6 @@ var testRange = function(top) {
fromClient.query('SELECT COUNT(*) FROM numbers', function(err, res) {
assert.ifError(err)
assert.equal(res.rows[0].count, top, 'expected ' + top + ' rows but got ' + res.rows[0].count)
assert.equal(stream.rowCount, top, 'expected ' + top + ' rows but db count is ' + stream.rowCount)
//console.log('found ', res.rows.length, 'rows')
countDone()
var firstRowDone = gonna('have correct result')
@@ -57,19 +58,3 @@ var testRange = function(top) {
}
testRange(1000)
var testSingleEnd = function() {
var fromClient = client()
fromClient.query('CREATE TEMP TABLE numbers(num int)')
var txt = 'COPY numbers FROM STDIN';
var stream = fromClient.query(copy(txt))
var count = 0;
stream.on('end', function() {
count++;
assert(count==1, '`end` Event was triggered ' + count + ' times');
if (count == 1) fromClient.end();
})
stream.end(Buffer('1\n'))
}
testSingleEnd()
+1 -46
View File
@@ -1,5 +1,3 @@
'use strict';
var assert = require('assert')
var gonna = require('gonna')
@@ -9,7 +7,6 @@ var concat = require('concat-stream')
var pg = require('pg')
var copy = require('../').to
var code = require('../message-formats')
var client = function() {
var client = new pg.Client()
@@ -25,18 +22,6 @@ var testConstruction = function() {
testConstruction()
var testComparators = function() {
var copy1 = copy();
copy1.pipe(concat(function(buf) {
assert(copy1._gotCopyOutResponse, 'should have received CopyOutResponse')
assert(!copy1._remainder, 'Message with no additional data (len=Int4Len+0) should not leave a remainder')
}))
copy1.end(new Buffer([code.CopyOutResponse, 0x00, 0x00, 0x00, 0x04]));
}
testComparators();
var testRange = function(top) {
var fromClient = client()
var txt = 'COPY (SELECT * from generate_series(0, ' + (top - 1) + ')) TO STDOUT'
@@ -88,35 +73,5 @@ var testInternalPostgresError = function() {
queryClient.end()
})
}
testInternalPostgresError()
var testNoticeResponse = function() {
// we use a special trick to generate a warning
// on the copy stream.
var queryClient = client()
var set = '';
set += 'SET SESSION client_min_messages = WARNING;'
set += 'SET SESSION standard_conforming_strings = off;'
set += 'SET SESSION escape_string_warning = on;'
queryClient.query(set, function(err, res) {
assert.equal(err, null, 'testNoticeResponse - could not SET parameters')
var runStream = function(callback) {
var txt = "COPY (SELECT '\\\n') TO STDOUT"
var stream = queryClient.query(copy(txt))
stream.on('data', function(data) {
})
stream.on('error', callback)
// make sure stream is pulled from
stream.pipe(concat(callback.bind(null,null)))
}
runStream(function(err) {
assert.equal(err, null, err)
queryClient.end()
})
})
}
testNoticeResponse();
-2
View File
@@ -1,5 +1,3 @@
'use strict';
require('./copy-from')
require('./copy-to')
require('./binary')